Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About me
About me
Page not in menu
This is a page not in th emain menu
Posts
publications
An Augmented Reality Application for Computer Engineering Curriculum
Published in International Journal of Informatics Technologies, 2017
Today, smart phones and tablet PCs have a huge application area due to their capabilities and ease of use. One of these application areas is education. Especially, supportive technologies have brought big innovations on teaching abstract concepts to the students. One of these technologies is Augmented Reality (AR) which moves graphic&animation usage one step towards. In this study, we shared our experiments on the usage of AR in computer engineering curriculum and presented the application that developed for supporting the abstract concepts of Discrete Mathematical Structures course with AR.
Recommended citation: ŞİMŞEK, M , TOKLU, S , ÖZSARAÇ, H , ZAVRAK, S , BAŞER, E , TAKGİL, B , KANBUR, Z . (2017). "An Augmented Reality Application for Computer Engineering Curriculum". International Journal of Informatics Technologies, 10 (1) , 47-0 . Retrieved from https://dergipark.org.tr/tr/pub/gazibtd/issue/27536/289674 https://dergipark.org.tr/tr/pub/gazibtd/issue/27536/289674
Leakage detection and localization on water transportation pipelines: a multi-label classification approach
Published in Neural Computing and Applications, 2017
One of the main problems of water transportation pipelines is leak which can cause water resources loss, possible human injuries, and damages to the environment. There are many studies in the literature focusing on detection and localization of leaks in the water pipeline systems. In this study, we have designed a wireless sensor network-based real-time monitoring system to detect and locate the leaks on multiple positions on water pipelines by using pressure data. At first, the pressure data are collected from wireless pressure sensor nodes. After that, unlike from the previous works in the literature, both the detection and localization of leakages are carried out by using multi-label learning methods. We have used three multi-label classification methods which are RAkELd, BRkNN, and BR with SVM. After the evaluation and comparison of the methods with each other, we observe that the RAkELd method performs best on almost all measures with the accuracy ratio of 98%. As a result, multi-label classification methods can be used on the detection and localization of the leaks in the pipeline systems successfully.
Recommended citation: Kayaalp, F., Zengin, A., Kara, R., Zavrak, S. "Leakage detection and localization on water transportation pipelines: a multi-label classification approach". Neural Computing and Applications 28, 2905–2914 (2017). https://doi.org/10.1007/s00521-017-2872-4. https://link.springer.com/article/10.1007/s00521-017-2872-4
The implementation of two-factor web authentication system based on facial recognition
Published in Global Journal of Computer Sciences: Theory and Research, 2017
In order to protect personal information on the web system and provide the security of transactions carried out at a high level, in this study, we propose a two-factor authentication mechanism based on facial recognition. Besides, we discuss some implementation details about the proposed method. The proposed method aims to bring a new approach to the authentication system to perform our online process with the highest security. In addition to the standard authentication systems, using face recognition as a secondary level of security will contribute to the emergence of a new authentication mechanism.
Recommended citation: Zavrak, S., Yilmaz, S., Bodur, H., & Toklu, S. (2017). "The implementation of two-factor web authentication system based on facial recognition". Global Journal of Computer Sciences: Theory and Research, 7(2), 92-101. https://un-pub.eu/ojs/index.php/gjcs/article/view/3448/3481
Anomaly-Based Intrusion Detection From Network Flow Features Using Variational Autoencoder
Published in IEEE Access, 2020
The rapid increase in network traffic has recently led to the importance of flow-based intrusion detection systems processing a small amount of traffic data. Furthermore, anomaly-based methods, which can identify unknown attacks are also integrated into these systems. In this study, the focus is concentrated on the detection of anomalous network traffic (or intrusions) from flow-based data using unsupervised deep learning methods with semi-supervised learning approach. More specifically, Autoencoder and Variational Autoencoder methods were employed to identify unknown attacks using flow features. In the experiments carried out, the flow-based features extracted out of network traffic data, including typical and different types of attacks, were used. The Receiver Operating Characteristics (ROC) and the area under ROC curve, resulting from these methods were calculated and compared with One-Class Support Vector Machine. The ROC curves were examined in detail to analyze the performance of the methods in various threshold values. The experimental results show that Variational Autoencoder performs, for the most part, better than Autoencoder and One-Class Support Vector Machine.
Recommended citation: S. Zavrak and M. İskefiyeli, "Anomaly-Based Intrusion Detection From Network Flow Features Using Variational Autoencoder", in IEEE Access, vol. 8, pp. 108346-108358, 2020, doi: 10.1109/ACCESS.2020.3001350 https://ieeexplore.ieee.org/document/9113298
Development and implementation of an analysis tool for direct current electrical circuits
Published in Computer Applications in Engineering Education, 2021
Electrical circuits constitute the core of many courses at the undergraduate level in electrical and electronics engineering. For most undergraduate students, learning and analyzing such circuits are a difficult process. A significant drawback of Simulation Program with Integrated Circuit Emphasis (SPICE)‐based simulation tools in terms of e‐learning is that they only generate circuit simulation outputs, such as the current and voltage of electrical elements contained in a particular circuit. The users are not provided with the detailed information about the steps that are followed to obtain the related outputs. This study describes the development of a new software tool, called ECDAT (a shorthand for the Electrical Circuit Description and Analysis Tool), which can serve as a practical component of electrical circuits courses. The developed tool currently analyzes simple direct electric circuits in a similar way as the existing circuit analysis and simulation ones, and it produces an output document that includes the certain equations and intermediate calculations, using the well‐known circuit laws differently from the previous works. Another contribution of the study is that, unlike the modified nodal analysis method used in SPICE‐based circuit analysis programs, it employs a graph analysis method for circuit analysis.
Recommended citation: H. Pehlivan, C. Atalar, and S. Zavrak, Development and implementation of an analysis tool for direct current electrical circuits, Comput. Appl. Eng. Educ., vol. 29, no. 5, pp. 1071–1086, Sep. 2021, doi: 10.1002/cae.22361 https://onlinelibrary.wiley.com/doi/full/10.1002/cae.22361
Real-Time Monitoring and Scalable Messaging of SCADA Networks Data: A Case Study on Cyber-Physical Attack Detection in Water Distribution System
Published in Electrical and Computer Engineering. ICECENG 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 2022
SCADA networks, which are widely used by governments around the world to run computers and applications that perform a wide range of important functions and provide critical services to their infrastructure, are becoming increasingly popular among organizations. Because of their critical role in the infrastructure, as well as the fact that they are a potential target for cyberattacks, they must be secured and protected in some way at all times. In this study, we propose a topic-based pub/sub messaging system based on Apache Spark and Apache Kafka for real-time monitoring and detection of cyber-physical attacks in SCADA systems, which can be used in conjunction with other currently available systems. There are a variety of traditional machine learning approaches used in conjunction with a deep learning encoded decoder algorithm to create the mechanism for attack detection. The performance results demonstrate that our system outperforms the current state of the art described in the literature in this field.
Recommended citation: Balta, S., Zavrak, S., Eken, S. (2022). Real-Time Monitoring and Scalable Messaging of SCADA Networks Data: A Case Study on Cyber-Physical Attack Detection in Water Distribution System. In: Seyman, M.N. (eds) Electrical and Computer Engineering. ICECENG 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 436. Springer, Cham. https://doi.org/10.1007/978-3-031-01984-5_17 https://link.springer.com/chapter/10.1007/978-3-031-01984-5_17
Flow-based intrusion detection on software-defined networks: a multivariate time series anomaly detection approach
Published in Neural Computing and Applications, 2023
In this study, we present and implement the SAnDet (SDN anomaly detector) architecture, an anomaly-based intrusion detection system designed to take advantage of the capabilities offered by software-defined networking (SDN) architecture, as a controller application. The SAnDet system is composed of three modules: statistics collection, anomaly detection, and anomaly prevention. In particular, we utilize replicator neural networks (RNN), which is a specialized variant of the autoencoder, and the LSTM-based encoder–decoder (EncDecAD) method, which is a special type of long short-term memory (LSTM) network that has demonstrated a strong performance on data series particularly, to identify unknown attacks using flow features collected from OpenFlow switches. In our experiments, we utilize flow-based features extracted from network traffic data containing various types of attacks as input to our models in the form of time series. We evaluate the performance of our methods using the accuracy and area under the receiver operating characteristic curve (AUC) metrics. Our experimental results demonstrate that EncDecAD outperforms RNN and that our approach offers several benefits over previously conducted research.
Recommended citation: Zavrak, S., Iskefiyeli, M. Flow-based intrusion detection on software-defined networks: a multivariate time series anomaly detection approach. Neural Comput & Applic (2023). https://doi.org/10.1007/s00521-023-08376-5 https://link.springer.com/article/10.1007/s00521-023-08376-5
Email spam detection using hierarchical attention hybrid deep learning method
Published in Expert Systems with Applications, 2023
Email is one of the most widely used ways to communicate, with millions of people and businesses relying on it to communicate and share knowledge and information on a daily basis. Nevertheless, the rise in email users has occurred a dramatic increase in spam emails in recent years. Considering the escalating number of spam emails, it has become crucial to devise effective strategies for spam detection. To tackle this challenge, this article proposes a novel technique for email spam detection that is based on a combination of convolutional neural networks, gated recurrent units, and attention mechanisms. During system training, the network is selectively focused on necessary parts of the email text. The usage of convolution layers to extract more meaningful, abstract, and generalizable features by hierarchical representation is the major contribution of this study. Additionally, this contribution incorporates cross-dataset evaluation, which enables the generation of more independent performance results from the model’s training dataset. According to cross-dataset evaluation results, the proposed technique advances the results of the present attention-based techniques by utilizing temporal convolutions, which give us more flexible receptive field sizes are utilized. The suggested technique’s findings are compared to those of state-of-the-art models and show that our approach outperforms them.
Recommended citation: Zavrak, S., & Yilmaz, S. (2023). Email spam detection using hierarchical attention hybrid deep learning method. Expert Systems with Applications, 233, 120977. https://doi.org/10.1016/J.ESWA.2023.120977 https://www.sciencedirect.com/science/article/abs/pii/S0957417423014793